from collections import OrderedDict
import torch
from models.faceland_d import FaceLanndInference_d
if __name__ == '__main__':
model = FaceLanndInference_d()
model_paths = ["./weights_d/0.0680_slim128_epoch_52.pth",
"./weights_d/0.0680_slim128_epoch_52.pth"]
if model_paths:
bone_dict = model.state_dict()
new_state_dict = OrderedDict()
data_len=len(model_paths)
for model_path in model_paths:
state_dict = torch.load(model_path)
for k, v in state_dict.items():
head = k[:7]
if head == 'module.':
tmp_name = k[7:] # remove `module.`
pytorch 多个模型 求平均
最新推荐文章于 2024-01-10 18:02:02 发布
本文详细探讨了如何在PyTorch框架下,对多个深度学习模型的预测输出进行平均,以提高预测的稳定性和准确性。通过实例代码展示了如何将不同模型的预测概率或特征向量进行加权平均,从而获得更可靠的综合预测结果。
摘要由CSDN通过智能技术生成